You’re out of free articles.
Log in
To continue reading, log in to your account.
Create a Free Account
To unlock more free articles, please create a free account.
Sign In or Create an Account.
By continuing, you agree to the Terms of Service and acknowledge our Privacy Policy
Welcome to Heatmap
Thank you for registering with Heatmap. Climate change is one of the greatest challenges of our lives, a force reshaping our economy, our politics, and our culture. We hope to be your trusted, friendly, and insightful guide to that transformation. Please enjoy your free articles. You can check your profile here .
subscribe to get Unlimited access
Offer for a Heatmap News Unlimited Access subscription; please note that your subscription will renew automatically unless you cancel prior to renewal. Cancellation takes effect at the end of your current billing period. We will let you know in advance of any price changes. Taxes may apply. Offer terms are subject to change.
Subscribe to get unlimited Access
Hey, you are out of free articles but you are only a few clicks away from full access. Subscribe below and take advantage of our introductory offer.
subscribe to get Unlimited access
Offer for a Heatmap News Unlimited Access subscription; please note that your subscription will renew automatically unless you cancel prior to renewal. Cancellation takes effect at the end of your current billing period. We will let you know in advance of any price changes. Taxes may apply. Offer terms are subject to change.
Create Your Account
Please Enter Your Password
Forgot your password?
Please enter the email address you use for your account so we can send you a link to reset your password:
AI has already changed weather forecasting forever.
It’s been a wild few years in the typically tedious world of weather predictions. For decades, forecasts have been improving at a slow and steady pace — the standard metric is that every decade of development leads to a one-day improvement in lead time. So today, our four-day forecasts are about as accurate as a one-day forecast was 30 years ago. Whoop-de-do.
Now thanks to advances in (you guessed it) artificial intelligence, things are moving much more rapidly. AI-based weather models from tech giants such as Google DeepMind, Huawei, and Nvidia are now consistently beating the standard physics-based models for the first time. And it’s not just the big names getting into the game — earlier this year, the 27-person team at Palo Alto-based startup Windborne one-upped DeepMind to become the world’s most accurate weather forecaster.
“What we’ve seen for some metrics is just the deployment of an AI-based emulator can gain us a day in lead time relative to traditional models,” Daryl Kleist, who works on weather model development at the National Oceanic and Atmospheric Administration, told me. That is, today’s two-day forecast could be as accurate as last year’s one-day forecast.
All weather models start by taking in data about current weather conditions. But from there, how they make predictions varies wildly. Traditional weather models like the ones NOAA and the European Centre for Medium-Range Weather Forecasts use rely on complex atmospheric equations based on the laws of physics to predict future weather patterns. AI models, on the other hand, are trained on decades of prior weather data, using the past to predict what will come next.
Kleist told me he certainly saw AI-based weather forecasting coming, but the speed at which it’s arriving and the degree to which these models are improving has been head-spinning. “There's papers coming out in preprints almost on a bi-weekly basis. And the amount of skill they've been able to gain by fine tuning these things and taking it a step further has been shocking, frankly,” he told me.
So what changed? As the world has seen with the advent of large language models like ChatGPT, AI architecture has gotten much more powerful, period. The weather models themselves are also in a cycle of continuous improvement — as more open source weather data becomes available, models can be retrained. Plus, the cost of computing power has come way down, making it possible for a small company like Windborne to train its industry-leading model.
Founded by a team of Stanford students and graduates in 2019, Windborne used off-the-shelf Nvidia gaming GPUs to train its AI model, called WeatherMesh — something the company’s CEO and co-founder, John Dean, told me wouldn’t have been possible five years ago. The company also operates its own fleet of advanced weather balloons, which gather data from traditionally difficult-to-access areas.
Standard weather balloons without onboard navigation typically ascend too high, overinflate, and pop within a matter of hours (thus becoming environmental waste, sad!). Since it’s expensive to do launches at sea or in areas without much infrastructure, there’s vast expanses of the globe where most balloons aren’t gathering any data at all.
Satellites can help, of course. But because they’re so far away, they can’t provide the same degree of fidelity. With modern electronics, though, Windborne found it could create a balloon that autonomously changes altitude and navigates to its intended target by venting gas to descend and dropping ballast to ascend.
“We basically took a lot of the innovations that lead to smartphones, global satellite communications, all of the last 20 years of progress in consumer electronics and other things and applied that to balloons,” Dean told me. In the past, the electronics needed to control Windborne’s system would have been too heavy — the balloon wouldn’t have gotten off the ground. But with today’s tiny tech, they can stay aloft for up to 40 days. Eventually, the company aims to recover and reuse at least 80% of its balloons.
The longer airtime allows Windborne to do more with less. While globally there are more than 1,000 conventional weather balloons launched every day, Dean told me, “We collect roughly on the order of 10% or 20% of the data that NOAA collects every day with only 100 launches per month.” In fact, NOAA is a customer of the startup — Windborne already makes millions in revenue selling its weather balloon data to various government agencies.
Now, with a potentially historic hurricane season ramping up, Windborne has the potential to provide the most accurate data on when and where a storm will touch down.
Earlier this year, the company used WeatherMesh to run a case study on Hurricane Ian, the Category 5 storm that hit Florida in September 2022, leading to over 150 fatalities and $112 billion in damages. Using only weather data that was publicly available at the time, the company looked at how accurately its model (had it existed back then) would have tracked the hurricane.
Very accurately, it turns out. Windborne’s predictions aligned neatly with the storm’s actual path, while the National Weather Service’s model was off by hundreds of kilometers. That impressed Khosla Ventures, which led the company’s $15 million Series A funding round earlier this month. “We haven’t seen meaningful innovation in weather since The Weather Channel in the 90s. Yet it’s a $100 billion market that touches essentially every industry,” Sven Strohband, a partner and managing director at Khosla Ventures, told me via email.
With this new funding, Windborne is scaling up its fleet of balloons as it prepares to commercialize. The money will also help Windborne advance its forecasting model, though Dean told me robust data collection is ultimately what will set the company apart. “In any kind of AI industry, whoever has the top benchmark at any given time, it’s going to fluctuate,” Dean said. “What matters is the model plus the unique datasets.”
Unlike Windborne, the tech giants with AI-based weather models — including, most recently, Microsoft — aren’t gathering their own data, instead drawing solely on publicly accessible information from legacy weather agencies.
But these agencies are starting to get into the game, too. The European Centre for Medium-Range Weather Forecasts has already created its own AI-based model, the Artificial Intelligence/Integrated Forecasting System, which it runs in parallel to its traditional model. NOAA, while a bit behind, is also looking to follow suit.
“In the end, we know we can't rely on these big tech companies to just keep developing stuff in good faith to give to us for free,” Kleist told me. Right now, many of the top AI-based weather models are open source. But who knows if that will last? “It's our mission to save lives and property. And we have to figure out how to do some of this development and operationalize it from our side, ourselves,” Kleist said, explaining that NOAA is currently prototyping some of its own AI-based models.
All of these agencies are in the early stages of AI modeling, which is why you likely haven’t noticed weather predictions making a pronounced leap in accuracy as of late. It’s all still considered quite experimental. “Physical models, the pro is we know the underlying assumptions we make. We understand them. We have decades of history of developing them and using them in operational settings,” Kleist told me. AI-based models are much more of a black box, and there’s questions surrounding how well they will perform when it comes to predicting rare weather events, for which there might be little to no historical data for the model to reference.
That hesitation might not last long, though. “To me it’s fairly obvious that most of the forecasts that would actually be used by users in the future will come from machine learning models,” Peter Dueben, head of Earth systems modeling at the European Centre for Medium Range Weather Forecasting, told me. “If you just want to get the weather forecast for the temperature in California tomorrow, then the machine learning model is typically the better choice,” he added.
That increased accuracy is going to matter a lot, not just for the average weather watcher, but also for specific industries and interest groups for whom precise predictions are paramount. “We can tailor the actual models to particular sectors, whether it's agriculture, energy, transportation,” Kleist told me, “and come up with information that's going to be at a very granular, specific level to a particular interest.” Think grid operators or renewable power generators who need to forecast demand or farmers trying to figure out the best time to irrigate their fields or harvest crops.
A major (and perhaps surprising) reason this type of customization is so easy is because once AI-based weather models are trained, they’re actually orders of magnitude cheaper and less computationally intensive to run than traditional models. All of this means, Kleist told me, that AI-based weather models are “going to be fundamentally foundational for what we do in the future, and will open up avenues to things we couldn't have imagined using our current physical-based modeling.”
Log in
To continue reading, log in to your account.
Create a Free Account
To unlock more free articles, please create a free account.
A conversation with VDE Americas CEO Brian Grenko.
This week’s Q&A is about hail. Last week, we explained how and why hail storm damage in Texas may have helped galvanize opposition to renewable energy there. So I decided to reach out to Brian Grenko, CEO of renewables engineering advisory firm VDE Americas, to talk about how developers can make sure their projects are not only resistant to hail but also prevent that sort of pushback.
The following conversation has been lightly edited for clarity.
Hiya Brian. So why’d you get into the hail issue?
Obviously solar panels are made with glass that can allow the sunlight to come through. People have to remember that when you install a project, you’re financing it for 35 to 40 years. While the odds of you getting significant hail in California or Arizona are low, it happens a lot throughout the country. And if you think about some of these large projects, they may be in the middle of nowhere, but they are taking hundreds if not thousands of acres of land in some cases. So the chances of them encountering large hail over that lifespan is pretty significant.
We partnered with one of the country’s foremost experts on hail and developed a really interesting technology that can digest radar data and tell folks if they’re developing a project what the [likelihood] will be if there’s significant hail.
Solar panels can withstand one-inch hail – a golfball size – but once you get over two inches, that’s when hail starts breaking solar panels. So it’s important to understand, first and foremost, if you’re developing a project, you need to know the frequency of those events. Once you know that, you need to start thinking about how to design a system to mitigate that risk.
The government agencies that look over land use, how do they handle this particular issue? Are there regulations in place to deal with hail risk?
The regulatory aspects still to consider are about land use. There are authorities with jurisdiction at the federal, state, and local level. Usually, it starts with the local level and with a use permit – a conditional use permit. The developer goes in front of the township or the city or the county, whoever has jurisdiction of wherever the property is going to go. That’s where it gets political.
To answer your question about hail, I don’t know if any of the [authority having jurisdictions] really care about hail. There are folks out there that don’t like solar because it’s an eyesore. I respect that – I don’t agree with that, per se, but I understand and appreciate it. There’s folks with an agenda that just don’t want solar.
So okay, how can developers approach hail risk in a way that makes communities more comfortable?
The bad news is that solar panels use a lot of glass. They take up a lot of land. If you have hail dropping from the sky, that’s a risk.
The good news is that you can design a system to be resilient to that. Even in places like Texas, where you get large hail, preparing can mean the difference between a project that is destroyed and a project that isn’t. We did a case study about a project in the East Texas area called Fighting Jays that had catastrophic damage. We’re very familiar with the area, we work with a lot of clients, and we found three other projects within a five-mile radius that all had minimal damage. That simple decision [to be ready for when storms hit] can make the complete difference.
And more of the week’s big fights around renewable energy.
1. Long Island, New York – We saw the face of the resistance to the war on renewable energy in the Big Apple this week, as protestors rallied in support of offshore wind for a change.
2. Elsewhere on Long Island – The city of Glen Cove is on the verge of being the next New York City-area community with a battery storage ban, discussing this week whether to ban BESS for at least one year amid fire fears.
3. Garrett County, Maryland – Fight readers tell me they’d like to hear a piece of good news for once, so here’s this: A 300-megawatt solar project proposed by REV Solar in rural Maryland appears to be moving forward without a hitch.
4. Stark County, Ohio – The Ohio Public Siting Board rejected Samsung C&T’s Stark Solar project, citing “consistent opposition to the project from each of the local government entities and their impacted constituents.”
5. Ingham County, Michigan – GOP lawmakers in the Michigan State Capitol are advancing legislation to undo the state’s permitting primacy law, which allows developers to evade municipalities that deny projects on unreasonable grounds. It’s unlikely the legislation will become law.
6. Churchill County, Nevada – Commissioners have upheld the special use permit for the Redwood Materials battery storage project we told you about last week.
Long Islanders, meanwhile, are showing up in support of offshore wind, and more in this week’s edition of The Fight.
Local renewables restrictions are on the rise in the Hawkeye State – and it might have something to do with carbon pipelines.
Iowa’s known as a renewables growth area, producing more wind energy than any other state and offering ample acreage for utility-scale solar development. This has happened despite the fact that Iowa, like Ohio, is home to many large agricultural facilities – a trait that has often fomented conflict over specific projects. Iowa has defied this logic in part because the state was very early to renewables, enacting a state portfolio standard in 1983, signed into law by a Republican governor.
But something else is now on the rise: Counties are passing anti-renewables moratoria and ordinances restricting solar and wind energy development. We analyzed Heatmap Pro data on local laws and found a rise in local restrictions starting in 2021, leading to nearly 20 of the state’s 99 counties – about one fifth – having some form of restrictive ordinance on solar, wind or battery storage.
What is sparking this hostility? Some of it might be counties following the partisan trend, as renewable energy has struggled in hyper-conservative spots in the U.S. But it may also have to do with an outsized focus on land use rights and energy development that emerged from the conflict over carbon pipelines, which has intensified opposition to any usage of eminent domain for energy development.
The central node of this tension is the Summit Carbon Solutions CO2 pipeline. As we explained in a previous edition of The Fight, the carbon transportation network would cross five states, and has galvanized rural opposition against it. Last November, I predicted the Summit pipeline would have an easier time under Trump because of his circle’s support for oil and gas, as well as the placement of former North Dakota Governor Doug Burgum as interior secretary, as Burgum was a major Summit supporter.
Admittedly, this prediction has turned out to be incorrect – but it had nothing to do with Trump. Instead, Summit is now stalled because grassroots opposition to the pipeline quickly mobilized to pressure regulators in states the pipeline is proposed to traverse. They’re aiming to deny the company permits and lobbying state legislatures to pass bills banning the use of eminent domain for carbon pipelines. One of those states is South Dakota, where the governor last month signed an eminent domain ban for CO2 pipelines. On Thursday, South Dakota regulators denied key permits for the pipeline for the third time in a row.
Another place where the Summit opposition is working furiously: Iowa, where opposition to the CO2 pipeline network is so intense that it became an issue in the 2020 presidential primary. Regulators in the state have been more willing to greenlight permits for the project, but grassroots activists have pressured many counties into some form of opposition.
The same counties with CO2 pipeline moratoria have enacted bans or land use restrictions on developing various forms of renewables, too. Like Kossuth County, which passed a resolution decrying the use of eminent domain to construct the Summit pipeline – and then three months later enacted a moratorium on utility-scale solar.
I asked Jessica Manzour, a conservation program associate with Sierra Club fighting the Summit pipeline, about this phenomenon earlier this week. She told me that some counties are opposing CO2 pipelines and then suddenly tacking on or pivoting to renewables next. In other cases, counties with a burgeoning opposition to renewables take up the pipeline cause, too. In either case, this general frustration with energy companies developing large plots of land is kicking up dust in places that previously may have had a much lower opposition risk.
“We painted a roadmap with this Summit fight,” said Jess Manzour, a campaigner with Sierra Club involved in organizing opposition to the pipeline at the grassroots level, who said zealous anti-renewables activists and officials are in some cases lumping these items together under a broad umbrella. ”I don’t know if it’s the people pushing for these ordinances, rather than people taking advantage of the situation.”